Credit score cards are a common risk control method in the financial industry.The bank is able to decide whether to issue a credit card to the applicant. Credit scores can objectively quantify the magnitude of risk.
We are assuming that if the customer paid very late payment (More than 60 days) We consider them as risky customer( Might not pay the bill in the future)
First, We used Logistic Regression to train our model but in that case accuracy(61.90%) not as much good. so, we decided to use Decision Tree Classifier(98.45%) to improve accuracy of model.
The model determines an applicant is 'good' or 'bad' client, based on given values of attributes.